index-advisor
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to instructions embedded within the database queries or schemas it analyzes.
- Ingestion points: External SQL queries, schema files, output from the schema-architect tool, and database metadata read during the dynamic analysis phase (SKILL.md).
- Boundary markers: Absent; there are no instructions to the agent to distinguish between data and embedded commands within the SQL or schema inputs.
- Capability inventory: The skill can write reports to the filesystem in both Markdown and JSON formats, and suggests SQL code for execution (SKILL.md).
- Sanitization: None identified; the skill does not specify validation or filtering of the ingested SQL content.
Audit Metadata